LLaMAntino-3-ANITA-8B-Inst-DPO-ITA: benchmark results
University of Bari's (swap-uniba) Italian-English fine-tune of Llama 3 8B Instruct, QLoRA SFT plus DPO alignment from the ANITA project. Provider: University of Bari. Released 2024-04-29. Access: Open.
Aggregate Rating 1449 ± 21, rank #1009 of 1656 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EVALITA - faq | 56.55 | CPS | 100 |
| Open LLM Leaderboard v1 - HellaSwag | 92.75 | Normalized accuracy (%) (10-shot) | 100 |
| Open LLM Leaderboard v1 - ARC Challenge | 74.57 | Normalized accuracy (%) (25-shot) | 99.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 75.93 | MC2 (%) (0-shot) | 95.8 |
| Open LLM Leaderboard v1 - MMLU | 66.85 | Accuracy (%) (5-shot) | 88.4 |
| EVALITA - relation-extraction | 42.14 | CPS | 87.2 |
| Open Italian LLM - MMLU-Pro (IT) | 30.11 | Accuracy (%) | 85.7 |
| Open LLM Leaderboard v1 - WinoGrande | 82 | Accuracy (%) (5-shot) | 81.7 |
| Open LLM Leaderboard - MuSR | 43.87 | Score | 77.3 |
| EVALITA - summarization-fanpage | 29.1 | CPS | 72.3 |
| Pinocchio Italian - Logica | 43.97 | Accuracy (%) | 70.5 |
| Open LLM Leaderboard v1 - GSM8K | 58.61 | Accuracy (%) (5-shot) | 70.4 |
Interactive version: theaggregate.ai/model?slug=llamantino-3-anita-8b-inst-dpo-ita · How It Works · Data refreshed daily, snapshot 2026-10-20.